ComfyUI Node
Hunyuan Image Latent To Video Latent
Copies the given latent's samples tensor along the time axis ((length - 1) // 4) + 1 times to form a longer latent (see EmptyHunyuanLatentVideo's implementation for why this specific number of copies is used). Then, prepares a noise_mask tensor of the same shape such that the value of the mask for a given time step is given by the function shown at https://www.desmos.com/calculator/vhw74mr1vh.
Hunyuan Image Latent To Video Latent
- latent
- LATENT
◄length49►
◄use_noise_masktrue►
◄noise_s20.00►
◄noise_o0.25►
◄noise_w0.05►
Categorylatent
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| length | INT | 491–40000 | The number of frames desired |
| latent | LATENT | The Hunyuan image latent to convert into a Hunyuan video latent | |
| use_noise_mask | BOOLEAN | true | Whether to include a noise mask |
| noise_s | FLOAT | 20.000–100 | The s (scale) parameter in the noise intensity function (see https://www.desmos.com/calculator/vhw74mr1vh) |
| noise_o | FLOAT | 0.25-2–2 | The o parameter (offset) in the noise intensity function (see https://www.desmos.com/calculator/vhw74mr1vh) |
| noise_w | FLOAT | 0.050–2 | The w parameter (width) in the noise intensity function (see https://www.desmos.com/calculator/vhw74mr1vh) |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| LATENT | LATENT | — |